add

2026-07-03 00:38:05 +09:00
parent 87eacd39b2
commit 86cad348b4
149 changed files with 24450 additions and 105 deletions
@@ -25,11 +25,14 @@ Use for sources that are central to one of these durable themes:
 - Quality engineering, security, supply-chain, infra reliability for AI/software systems
 - Technical writeups with implementation details likely to be referenced later
 - Loop-engineering style agent operations: discovery, handoff, independent verification, persistence, scheduling, evaluator separation, and state/log design for autonomous jobs
+- Framework-level workflow orchestration for agents: typed graph execution, reusable node/tool/agent primitives, durable pause/resume, human-in-the-loop interrupts, retry/concurrency controls, branch/session isolation, and telemetry that makes loops observable and replayable
 - AI-agent operator observability and control surfaces: monitoring multiple coding agents, local process/port/session visibility, rate-limit/context tracking, approval flows, and mobile/terminal dashboards for agent operations
 - Minimal, observable agent harnesses that expose context/session/tool/process state clearly, especially when they document trade-offs around provider abstraction, terminal/tmux workflows, sub-agents, MCP, permissions, or worktree-based isolation
- Agent-oriented CLI/tool design that reduces model guesswork with CLI-owned usage guides, JSON-first output, actionable errors, search/read separation, stale-state metadata, safe defaults, and few flags
- Code-to-knowledge and code-to-documentation systems that generate repo Wikis, C4 architecture views, diagrams, or durable onboarding material from source code, especially when they address documentation drift and review workflows
- Agent identity/security standards and operational controls, especially MCP authorization, Cross App Access/XAA, least privilege, audit logs, and supply-chain risks around agents
+- Agent-oriented CLI/tool design that reduces model guesswork with CLI-owned usage guides, JSON-first output, actionable errors, search/read separation, stale-state metadata, safe defaults, few flags, discoverable command trees, job controls, and bundled agent skills
+- Implementation-derived quality metrics that turn test traces, routes, APIs/RPCs, coverage denominators, evaluator outputs, or runtime evidence into durable feedback loops for development and release decisions
+- Code-to-knowledge and code-to-documentation systems that generate repo Wikis, C4 architecture views, diagrams, or durable onboarding material from source code, especially when they address documentation drift, agent instruction-file integration, scheduled diff-based updates, traceability, and review workflows
+- Agent identity/security standards and operational controls, especially MCP authorization, Cross App Access/XAA, least privilege, audit logs, command-execution guards, sandbox/approval boundaries, and supply-chain risks around agents
+- Browser-agent harnesses with concrete tool surfaces: DOM/network/console/screenshot/page-interaction access, local browser MCP servers, tab/session boundaries, performance checks, and accessibility checks that make UI debugging verifiable by agents
 - Human-gated AI security workflows that reduce maintainer burden: vulnerability discovery, verification, patch drafting, responsible disclosure, release monitoring, and false-positive suppression before any report leaves the operator's workspace
 - Niche, exciting design/hack/Hacker News-like material, especially when it exposes an unusual technique, tool, interface, or way of thinking
 - Public-interest/public-sector technology, civic infrastructure, accessibility (a11y), inclusive design, and systems that make services more usable or equitable